My dataset have 92 images and 2 label only. Training is still in progress. What should I do? I need to test today for this Model. I’m very urgent. Please help me.
Hi @mayhtikeswe ,
I can only think of a couple of reasons why your training is taking longer than it is supposed to be.
- Image size/ resolution - the higher the resolution the more complex the model can get resulting in longer training duration, same goes for having lots of samples with different sizes/ resolution. You can review the best practices when preparing data for an image classification model.
The training data should be as close as possible to the data on which predictions are to be made. For example, if your use case involves blurry and low-resolution images (such as from a security camera), your training data should be composed of blurry, low-resolution images. In general, you should also consider providing multiple angles, resolutions, and backgrounds for your training images.- Machine resources - a powerful machine will be able to train the model faster. If you happen to have a complex model in a less powerful machine, it may take several days to train the model.
You might want to consider using a smaller dataset/ images as it can reduce the time needed for training and run your model on a more powerful machine so it can train faster.
I hope this helps.